Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 09 Mar 2001 16:26:30 -0800
From:      Mike Smith <msmith@freebsd.org>
To:        =?ISO-8859-1?Q?G=E9rard_Roudier?= <groudier@club-internet.fr>
Cc:        Joe Albowicz <joe@CS.UCLA.EDU>, freebsd-hackers@FreeBSD.ORG
Subject:   Re: aic7xxx driver & SCBs 
Message-ID:  <200103100026.f2A0QUs11068@mass.dis.org>
In-Reply-To: Your message of "Fri, 09 Mar 2001 21:47:45 %2B0100." <Pine.LNX.4.10.10103092108400.1731-100000@linux.local> 

next in thread | previous in thread | raw e-mail | index | archive | help
> =

> On Fri, 9 Mar 2001, Mike Smith wrote:
> =

> > Joe; it looks like you have some funny ideas about something that's n=
ot =

> > actually very relevant.  I assume that you have already gone and boug=
ht =

> > Monster Cable(tm) SCSI cables, and that you have the special =

> > oxygen-free-copper SCSI controller PCBs, because none of this is goin=
g to =

> > mean anything unless you have.
> =

> Pardon and sorry, Mike. It is rather your reply that looks funny to me.=


It's meant to be funny.  Telling someome straight up that they're being =

silly isn't very amusing, so I like to improve things when I can.

> The number of SCBs in (both) the Linux and FreeBSD aic7xxx driver(s) is=

> very relevant in my opinion given that it is just the maximum of SCSI
> command contexts the driver can handle (i.e. maximum number of outstand=
ing
> IOs).

I'm not referring to the number being relevant, rather I'm referring to =

the percieved need that Joe has to tune said number.

> > > I'd like to ask if anyone can share any knowledge about how/if the =
number
> > > of SCBs affects performace for scsi drives.
> > =

> > If you don't have enough SCBs, you can't deliver enough commands to y=
our =

> > drive(s) to keep them busy.
> =

> Being busy does not imply doing a good job. You can get a device full b=
usy
> using only 2 simultaneous IOs for this device. Using more can allow the=

> device to perform optimizations based on actual head positions and
> possibly coalesce data transfers when possible, for example.

That's a better way of putting it, for sure.

> > > Also I would like to be able to configure the number of SCBs that t=
he scsi
> > > driver uses.  With Linux this parameter for the aic7xxx driver can =
be
> > > configured via "make menuconfig" step of the kernel build process. =
 Is
> > > there a similiar way to configure this varible for BSD?  Or do I ha=
ve to
> > > start hacking on the driver code?
> > =

> > You can't do that.  Firstly, there isn't a "SCSI driver", secondly th=
ere
> > are several different sorts of objects that map to what you, coming f=
rom
> > the Linux world, would call an SCB, and thirdly, the CAM subsystem
> > components have a much better idea than you do how many of these that=
 are
> > needed, and will allocate them as necessary.
> =

> You should have been more accurate here, in my opinion. Vague explanati=
ons =

> are worse than no explanations at all, in my opinion.

I find this amusing, mostly because I'm usually asked to dumb down my =

explanations so that people can understand them. 8)  Your exposition does=
 =

of course give a much more detailed view of the issues.

> Btw, your reply let me think that you want to discourage people to hack=
 =

> our source code or to try to understand how it works. Colour me very
> surprised. :-)

Actually, quite the opposite.  I'd much rather have Joe go look at the =

source and tools himself than sit here and try to explain it all to him. =
 =

However, I'd take even money on a request like this being from someone =

that is expecting everything else to be just like what he's already used =

to, and the first step is just to convince them that that's not really =

the case...

-- =

=2E.. every activity meets with opposition, everyone who acts has his
rivals and unfortunately opponents also.  But not because people want
to be opponents, rather because the tasks and relationships force
people to take different points of view.  [Dr. Fritz Todt]
           V I C T O R Y   N O T   V E N G E A N C E



To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-hackers" in the body of the message




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200103100026.f2A0QUs11068>